Deep-Learning-Assisted Volume Visualization.
Ontology highlight
ABSTRACT:
SUBMITTER: Cheng HC
PROVIDER: S-EPMC8369530 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.
| S-EPMC9097578 | biostudies-literature
Project description:The growth of underwater robotic applications in ocean exploration and research has created an urgent need for effective tactile sensing. Here, we propose an underwater 3-dimensional tactile tensegrity (U3DTT) based on soft self-powered triboelectric nanogenerators and deep-learning-assisted data analytics. This device can measure and distinguish the magnitude, location, and orientation of perturbations in real time from both flow field and interaction with obstacles and provide collision protection for underwater vehicles operation. It is enabled by the structure that mimics terrestrial animals' musculoskeletal systems composed of both stiff bones and stretchable muscles. Moreover, when successfully integrated with underwater vehicles, the U3DTT shows advantages of multiple degrees of freedom in its shape modes, an ultrahigh sensitivity, and fast response times with a low cost and conformability. The real-time 3-dimensional pose of the U3DTT has been predicted with an average root-mean-square error of 0.76 in a water pool, indicating that this developed U3DTT is a promising technology in vehicles with tactile feedback.
| S-EPMC10013964 | biostudies-literature
Project description:Engineering simulation accelerates the development of reliable and repeatable design processes in various domains. However, the computing resource consumption is dramatically raised in the whole development processes. Making the most of these simulation data becomes more and more important in modern industrial product design. In the present study, we proposed a workflow comprised of a series of machine learning algorithms (mainly deep neuron networks) to be an alternative to the numerical simulation. We have applied the workflow to the field of dental implant design process. The process is based on a complex, time-dependent, multi-physical biomechanical theory, known as mechano-regulatory method. It has been used to evaluate the performance of dental implants and to assess the tissue recovery after the oral surgery procedures. We provided a deep learning network (DLN) with calibrated simulation data that came from different simulation conditions with experimental verification. The DLN achieves nearly exact result of simulated bone healing history around implants. The correlation of the predicted essential physical properties of surrounding bones (e.g. strain and fluid velocity) and performance indexes of implants (e.g. bone area and bone-implant contact) were greater than 0.980 and 0.947, respectively. The testing AUC values for the classification of each tissue phenotype were ranging from 0.90 to 0.99. The DLN reduced hours of simulation time to seconds. Moreover, our DLN is explainable via Deep Taylor decomposition, suggesting that the transverse fluid velocity, upper and lower parts of dental implants are the keys that influence bone healing and the distribution of tissue phenotypes the most. Many examples of commercial dental implants with designs which follow these design strategies can be found. This work demonstrates that DLN with proper network design is capable to replace complex, time-dependent, multi-physical models/theories, as well as to reveal the underlying features without prior professional knowledge.
| S-EPMC8602721 | biostudies-literature
Project description:We used arrays of bioprinted renal epithelial cell spheroids for toxicity testing with cisplatin. The concentration-dependent cell death rate was determined using a lactate dehydrogenase assay. Bioprinted spheroids showed enhanced sensitivity to the treatment in comparison to monolayers of the same cell type. The measured dose-response curves revealed an inhibitory concentration of the spheroids of IC 50 = 9 ± 3 μM in contrast to the monolayers with IC 50 = 17 ± 2 μM. Fluorescent labeling of a nephrotoxicity biomarker, kidney injury molecule 1 indicated an accumulation of the molecule in the central lumen of the spheroids. Finally, we tested an approach for an automatic readout of toxicity based on microscopic images with deep learning. Therefore, we created a dataset comprising images of single spheroids, with corresponding labels of the determined cell death rates for training. The algorithm was able to distinguish between three classes of no, mild, and severe treatment effects with a balanced accuracy of 78.7%.
| S-EPMC9186384 | biostudies-literature
Project description:Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc.
| S-EPMC5655781 | biostudies-literature
Project description:PurposeVolumetric and health assessment of the liver is crucial to avoid poor post-operative outcomes following liver resection surgery. No current methods allow for concurrent and accurate measurement of both Couinaud segmental volumes for future liver remnant estimation and liver health using non-invasive imaging. In this study, we demonstrate the accuracy and precision of segmental volume measurements using new medical software, Hepatica™.MethodsMRI scans from 48 volunteers from three previous studies were used in this analysis. Measurements obtained from Hepatica™ were compared with OsiriX. Time required per case with each software was also compared. The performance of technicians and experienced radiologists as well as the repeatability and reproducibility were compared using Bland-Altman plots and limits of agreement.ResultsHigh levels of agreement and lower inter-operator variability for liver volume measurements were shown between Hepatica™ and existing methods for liver volumetry (mean Dice score 0.947 ± 0.010). A high consistency between technicians and experienced radiologists using the device for volumetry was shown (± 3.5% of total liver volume) as well as low inter-observer and intra-observer variability. Tight limits of agreement were shown between repeated Couinaud segment volume (+ 3.4% of whole liver), segmental liver fibroinflammation and segmental liver fat measurements in the same participant on the same scanner and between different scanners. An underestimation of whole-liver volume was observed between three non-reference scanners.ConclusionHepatica™ produces accurate and precise whole-liver and Couinaud segment volume and liver tissue characteristic measurements. Measurements are consistent between trained technicians and experienced radiologists.
| S-EPMC8776724 | biostudies-literature
Project description:Machine learning approaches have had tremendous success in various disciplines. However, such success highly depends on the size and quality of datasets. Scientific datasets are often small and difficult to collect. Currently, improving machine learning performance for small scientific datasets remains a major challenge in many academic fields, such as bioinformatics or medical science. Gradient boosting decision tree (GBDT) is typically optimal for small datasets, while deep learning often performs better for large datasets. This work reports a boosting tree-assisted multitask deep learning (BTAMDL) architecture that integrates GBDT and multitask deep learning (MDL) to achieve near-optimal predictions for small datasets when there exists a large dataset that is well correlated to the small datasets. Two BTAMDL models are constructed, one utilizing purely MDL output as GBDT input while the other admitting additional features in GBDT input. The proposed BTAMDL models are validated on four categories of datasets, including toxicity, partition coefficient, solubility, and solvation. It is found that the proposed BTAMDL models outperform the current state-of-the-art methods in various applications involving small datasets.
| S-EPMC7350172 | biostudies-literature
Project description:BackgroundAccurate assessment of the percentage total body surface area (%TBSA) of burn wounds is crucial in the management of burn patients. The resuscitation fluid and nutritional needs of burn patients, their need for intensive unit care, and probability of mortality are all directly related to %TBSA. It is difficult to estimate a burn area of irregular shape by inspection. Many articles have reported discrepancies in estimating %TBSA by different doctors.ObjectiveWe propose a method, based on deep learning, for burn wound detection, segmentation, and calculation of %TBSA on a pixel-to-pixel basis.MethodsA 2-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected from medical records and labeled by burn surgeons, and the data set was then input into 2 deep learning architectures, U-Net and Mask R-CNN, each configured with 2 different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another data set, which was also input into U-Net and Mask R-CNN to segment the hands. The %TBSA of burn wounds was then calculated by comparing the pixels of mask areas on images of the burn wound and hand of the same patient according to the rule of hand, which states that one's hand accounts for 0.8% of TBSA.ResultsA total of 2591 images of burn wounds were collected and labeled to form the burn wound data set. The data set was randomly split into training, validation, and testing sets in a ratio of 8:1:1. Four hundred images of volar hands were collected and labeled to form the hand data set, which was also split into 3 sets using the same method. For the images of burn wounds, Mask R-CNN with ResNet101 had the best segmentation result with a Dice coefficient (DC) of 0.9496, while U-Net with ResNet101 had a DC of 0.8545. For the hand images, U-Net and Mask R-CNN had similar performance with DC values of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet101 had on average less deviation (0.115% TBSA) from the ground truth than burn surgeons.ConclusionsThis is one of the first studies to diagnose all depths of burn wounds and convert the segmentation results into %TBSA using different deep learning models. We aimed to assist medical staff in estimating burn size more accurately, thereby helping to provide precise care to burn victims.
| S-EPMC8686480 | biostudies-literature
Project description:A comparative analysis of animal behavior (e.g., male vs. female groups) has been widely used to elucidate behavior specific to one group since pre-Darwinian times. However, big data generated by new sensing technologies, e.g., GPS, makes it difficult for them to contrast group differences manually. This study introduces DeepHL, a deep learning-assisted platform for the comparative analysis of animal movement data, i.e., trajectories. This software uses a deep neural network based on an attention mechanism to automatically detect segments in trajectories that are characteristic of one group. It then highlights these segments in visualized trajectories, enabling biologists to focus on these segments, and helps them reveal the underlying meaning of the highlighted segments to facilitate formulating new hypotheses. We tested the platform on a variety of trajectories of worms, insects, mice, bears, and seabirds across a scale from millimeters to hundreds of kilometers, revealing new movement features of these animals.
| S-EPMC7576204 | biostudies-literature
Project description:Generalizability of deep-learning (DL) model performance is not well understood and uses anecdotal assumptions for increasing training data to improve segmentation of medical images. We report statistical methods for visual interpretation of DL models trained using ImageNet initialization with natural-world (T II) and supervised learning with medical images (L MI) for binary segmentation of skin cancer, prostate tumors, and kidneys. An algorithm for computation of Dice scores from union and intersections of individual output masks was developed for synergistic segmentation by T II and L MI models. Stress testing with non-Gaussian distributions of infrequent clinical labels and images showed that sparsity of natural-world and domain medical images can counterintuitively reduce type I and type II errors of DL models. A toolkit of 30 T II and L MI models, code, and visual outputs of 59,967 images is shared to identify the target and non-target medical image pixels and clinical labels to explain the performance of DL models.
| S-EPMC9017181 | biostudies-literature